© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43660
    Prev
    Next
    INDEX
    Explanations

    money, angle, line, American

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cnemidophorus
    0.58
     Indus
    0.56
    瞓
    0.55
     Prong
    0.54
     சிகி
    0.54
     Kannada
    0.53
     Pronghorn
    0.53
    )=$
    0.52
     Bede
    0.52
     XIII
    0.52
    POSITIVE LOGITS
    (
    0.68
    *
    0.59
     steering
    0.53
     equalization
    0.52
     staircase
    0.51
    fir
    0.51
    stere
    0.50
     cracking
    0.50
     flooring
    0.49
    **
    0.49
    Activations Density 0.000%

    No Known Activations